© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56755
    Prev
    Next
    INDEX
    Explanations

    writing and output streams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     reading
    -2.64
    Reading
    -2.16
     read
    -2.16
     Reading
    -2.05
     reads
    -1.98
    reading
    -1.96
     READING
    -1.77
    读取
    -1.70
    READING
    -1.62
     Reads
    -1.60
    POSITIVE LOGITS
     writing
    1.66
     writer
    1.63
     write
    1.59
     Write
    1.59
     WRITE
    1.49
    write
    1.49
    Write
    1.47
    FileWriter
    1.45
    StreamWriter
    1.41
     writers
    1.41
    Activations Density 0.066%

    No Known Activations